{"id":"https://openalex.org/W4391020645","doi":"https://doi.org/10.1109/cdc49753.2023.10383691","title":"On the Convergence of Natural Policy Gradient and Mirror Descent-Like Policy Methods for Average-Reward MDPs","display_name":"On the Convergence of Natural Policy Gradient and Mirror Descent-Like Policy Methods for Average-Reward MDPs","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4391020645","doi":"https://doi.org/10.1109/cdc49753.2023.10383691"},"language":"en","primary_location":{"id":"doi:10.1109/cdc49753.2023.10383691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383691","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001386822","display_name":"Yashaswini Murthy","orcid":"https://orcid.org/0000-0002-8788-6873"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yashaswini Murthy","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Coordinated Science Lab,Department of Electrical and Computer Engineering,Urbana,IL,USA,61801"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Coordinated Science Lab,Department of Electrical and Computer Engineering,Urbana,IL,USA,61801","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078518595","display_name":"R. Srikant","orcid":"https://orcid.org/0000-0003-1483-5204"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Srikant","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Coordinated Science Lab,Department of Electrical and Computer Engineering,Urbana,IL,USA,61801"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Coordinated Science Lab,Department of Electrical and Computer Engineering,Urbana,IL,USA,61801","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5001386822"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.1748,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59600978,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1979","last_page":"1984"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7272339463233948},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.6633063554763794},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6279541254043579},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5837644934654236},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5486814975738525},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5398411750793457},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4976842701435089},{"id":"https://openalex.org/keywords/discounting","display_name":"Discounting","score":0.4815564453601837},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.47405073046684265},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.4717484414577484},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4574323296546936},{"id":"https://openalex.org/keywords/descent","display_name":"Descent (aeronautics)","score":0.4188283085823059},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2867509126663208},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2105662226676941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17496120929718018},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.1676233410835266},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11314401030540466},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.09257569909095764},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.050906747579574585}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7272339463233948},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.6633063554763794},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6279541254043579},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5837644934654236},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5486814975738525},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5398411750793457},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4976842701435089},{"id":"https://openalex.org/C6177178","wikidata":"https://www.wikidata.org/wiki/Q10998070","display_name":"Discounting","level":2,"score":0.4815564453601837},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47405073046684265},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.4717484414577484},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4574323296546936},{"id":"https://openalex.org/C2776637919","wikidata":"https://www.wikidata.org/wiki/Q624380","display_name":"Descent (aeronautics)","level":2,"score":0.4188283085823059},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2867509126663208},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2105662226676941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17496120929718018},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.1676233410835266},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11314401030540466},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.09257569909095764},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.050906747579574585},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc49753.2023.10383691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383691","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1497026160","https://openalex.org/W1505731132","https://openalex.org/W1549353711","https://openalex.org/W1553320709","https://openalex.org/W1986389067","https://openalex.org/W1991513691","https://openalex.org/W2074680702","https://openalex.org/W2081374871","https://openalex.org/W2094387729","https://openalex.org/W2101242010","https://openalex.org/W2119567691","https://openalex.org/W2123114919","https://openalex.org/W2130801532","https://openalex.org/W2143496582","https://openalex.org/W2156737235","https://openalex.org/W2173945562","https://openalex.org/W2963630259","https://openalex.org/W3103047293","https://openalex.org/W3127686539","https://openalex.org/W3171210634","https://openalex.org/W3178729124","https://openalex.org/W3211768774","https://openalex.org/W3217314940","https://openalex.org/W4214717370","https://openalex.org/W4221150902","https://openalex.org/W4226246290","https://openalex.org/W4229915002","https://openalex.org/W4315471814","https://openalex.org/W4319323297","https://openalex.org/W4323710169","https://openalex.org/W4381739798","https://openalex.org/W6675043515","https://openalex.org/W6679257226","https://openalex.org/W6682998330","https://openalex.org/W6683195989","https://openalex.org/W6759637383","https://openalex.org/W6765478815","https://openalex.org/W6769500229","https://openalex.org/W6779284943","https://openalex.org/W6780486084","https://openalex.org/W6786084949","https://openalex.org/W6803871076","https://openalex.org/W6810551561","https://openalex.org/W6849829952","https://openalex.org/W6850386099"],"related_works":["https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W4231621013","https://openalex.org/W4362706668","https://openalex.org/W2015288657","https://openalex.org/W3008318776","https://openalex.org/W2041416246","https://openalex.org/W3020853991"],"abstract_inverted_index":{"It":[0],"is":[1],"now":[2],"well":[3],"known":[4],"that":[5,53],"Natural":[6],"Policy":[7],"Gradient":[8],"(NPG)":[9],"globally":[10],"converges":[11,56],"for":[12,37,57,90],"discounted-reward":[13],"MDPs":[14,39,59],"in":[15,60],"the":[16,25,42],"tabular":[17],"setting,":[18],"with":[19],"perfect":[20],"value":[21],"function":[22],"estimates.":[23],"However,":[24],"result":[26,36],"cannot":[27],"be":[28,74],"directly":[29],"used":[30],"to":[31,46,65,87],"obtain":[32],"a":[33,77],"corresponding":[34],"convergence":[35],"average-reward":[38,58],"by":[40],"letting":[41],"discount":[43],"factor":[44],"tend":[45],"one.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,83],"prove":[52],"NPG":[54,71],"also":[55,73],"which":[61],"each":[62],"policy":[63,81],"leads":[64],"an":[66],"irreducible":[67],"Markov":[68],"chain.":[69],"Since":[70],"can":[72],"interpreted":[75],"as":[76],"mirror":[78,91],"descent":[79],"based":[80],"method,":[82],"then":[84],"discuss":[85],"extensions":[86],"non-tabular":[88],"settings":[89],"descent-based":[92],"methods.":[93]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}